Paper Group NAWR 5
BiLSTM-CRF for Persian Named-Entity Recognition ArmanPersoNERCorpus: the First Entity-Annotated Persian Dataset. CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles. The Neural Hype and Comparisons Against Weak Baselines. Evaluating bilingual word embeddings on the long tail. Towards Experienced Anomaly …
BiLSTM-CRF for Persian Named-Entity Recognition ArmanPersoNERCorpus: the First Entity-Annotated Persian Dataset
| Title | BiLSTM-CRF for Persian Named-Entity Recognition ArmanPersoNERCorpus: the First Entity-Annotated Persian Dataset |
| Authors | Hanieh Poostchi, Ehsan Zare Borzeshi, Massimo Piccardi |
| Abstract | |
| Tasks | Machine Translation, Named Entity Recognition, Text Summarization, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1701/ |
| https://www.aclweb.org/anthology/L18-1701 | |
| PWC | https://paperswithcode.com/paper/bilstm-crf-for-persian-named-entity |
| Repo | https://github.com/HaniehP/PersianNER |
| Framework | none |
CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles
| Title | CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles |
| Authors | N. Dinesh Reddy, Minh Vo, Srinivasa G. Narasimhan |
| Abstract | Despite significant research in the area, reconstruction of multiple dynamic rigid objects (eg. vehicles) observed from wide-baseline, uncalibrated and unsynchronized cameras, remains hard. On one hand, feature tracking works well within each view but is hard to correspond across multiple cameras with limited overlap in fields of view or due to occlusions. On the other hand, advances in deep learning have resulted in strong detectors that work across different viewpoints but are still not precise enough for triangulation-based reconstruction. In this work, we develop a framework to fuse both the single-view feature tracks and multi-view detected part locations to significantly improve the detection, localization and reconstruction of moving vehicles, even in the presence of strong occlusions. We demonstrate our framework at a busy traffic intersection by reconstructing over 62 vehicles passing within a 3-minute window. We evaluate the different components within our framework and compare to alternate approaches such as reconstruction using tracking-by-detection. |
| Tasks | 3D Reconstruction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Reddy_CarFusion_Combining_Point_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Reddy_CarFusion_Combining_Point_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/carfusion-combining-point-tracking-and-part |
| Repo | https://github.com/dineshreddy91/carfusion_to_coco |
| Framework | none |
The Neural Hype and Comparisons Against Weak Baselines
| Title | The Neural Hype and Comparisons Against Weak Baselines |
| Authors | Jimmy Lin |
| Abstract | Recently, the machine learning community paused in a moment of self-reflection. In a widely discussed paper at ICLR 2018, Sculley et al. wrote: “We observe that the rate of empirical advancement may not have been matched by consistent increase in the level of empirical rigor across the field as a whole.” Their primary complaint is the development of a “research and publication culture that emphasizes wins” (emphasis in original), which typically means “demonstrating that a new method beats previous methods on a given task or benchmark”. An apt description might be “leaderboard chasing”-and for many vision and NLP tasks, this isn’t a metaphor. There are literally centralized leaderboards1 that track incremental progress, down to the fifth decimal point, some persisting over years, accumulating dozens of entries. Sculley et al. remind us that “the goal of science is not wins, but knowledge”. The structure of the scientific enterprise today (pressure to publish, pace of progress, etc.) means that “winning” and “doing good science” are often not fully aligned. To wit, they cite a number of papers showing that recent advances in neural networks could very well be attributed to mundane issues like better hyperparameter optimization. Many results can’t be reproduced, and some observed improvements might just be noise. |
| Tasks | Ad-Hoc Information Retrieval, Hyperparameter Optimization |
| Published | 2018-12-01 |
| URL | https://dl.acm.org/citation.cfm?id=3308781 |
| http://sigir.org/wp-content/uploads/2019/01/p040.pdf | |
| PWC | https://paperswithcode.com/paper/the-neural-hype-and-comparisons-against-weak |
| Repo | https://github.com/castorini/Anserini |
| Framework | none |
Evaluating bilingual word embeddings on the long tail
| Title | Evaluating bilingual word embeddings on the long tail |
| Authors | Fabienne Braune, Viktor Hangya, Tobias Eder, Alex Fraser, er |
| Abstract | Bilingual word embeddings are useful for bilingual lexicon induction, the task of mining translations of given words. Many studies have shown that bilingual word embeddings perform well for bilingual lexicon induction but they focused on frequent words in general domains. For many applications, bilingual lexicon induction of rare and domain-specific words is of critical importance. Therefore, we design a new task to evaluate bilingual word embeddings on rare words in different domains. We show that state-of-the-art approaches fail on this task and present simple new techniques to improve bilingual word embeddings for mining rare words. We release new gold standard datasets and code to stimulate research on this task. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2030/ |
| https://www.aclweb.org/anthology/N18-2030 | |
| PWC | https://paperswithcode.com/paper/evaluating-bilingual-word-embeddings-on-the |
| Repo | https://github.com/braunefe/BWEeval |
| Framework | none |
Towards Experienced Anomaly Detector through Reinforcement Learning
| Title | Towards Experienced Anomaly Detector through Reinforcement Learning |
| Authors | Chengqiang Huang, Yulei Wu, Yuan Zuo, Ke Pei, Geyong Min |
| Abstract | This abstract proposes a time series anomaly detector which 1) makes no assumption about the underlying mechanism of anomaly patterns, 2) refrains from the cumbersome work of threshold setting for good anomaly detection performance under specific scenarios, and 3) keeps evolving with the growth of anomaly detection experience. Essentially, the anomaly detector is powered by the Recurrent Neural Network (RNN) and adopts the Reinforcement Learning (RL) method to achieve the self-learning process. Our initial experiments demonstrate promising results of using the detector in network time series anomaly detection problems. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2018-04-29 |
| URL | https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/16048 |
| https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPDFInterstitial/16048/16481 | |
| PWC | https://paperswithcode.com/paper/towards-experienced-anomaly-detector-through |
| Repo | https://github.com/chengqianghuang/exp-anomaly-detector |
| Framework | tf |
Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data
| Title | Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data |
| Authors | Guanghui Qin, Jin-Ge Yao, Xuening Wang, Jinpeng Wang, Chin-Yew Lin |
| Abstract | Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms. In this paper, we attempt at learning explicit latent semantic annotations from paired structured tables and texts, establishing correspondences between various types of values and texts. We model the joint probability of data fields, texts, phrasal spans, and latent annotations with an adapted semi-hidden Markov model, and impose a soft statistical constraint to further improve the performance. As a by-product, we leverage the induced annotations to extract templates for language generation. Experimental results suggest the feasibility of the setting in this study, as well as the effectiveness of our proposed framework. |
| Tasks | Language Acquisition, Text Generation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1411/ |
| https://www.aclweb.org/anthology/D18-1411 | |
| PWC | https://paperswithcode.com/paper/learning-latent-semantic-annotations-for |
| Repo | https://github.com/hiaoxui/D2T-Grounding |
| Framework | none |
Measuring the Diversity of Automatic Image Descriptions
| Title | Measuring the Diversity of Automatic Image Descriptions |
| Authors | Emiel van Miltenburg, Desmond Elliott, Piek Vossen |
| Abstract | Automatic image description systems typically produce generic sentences that only make use of a small subset of the vocabulary available to them. In this paper, we consider the production of generic descriptions as a lack of diversity in the output, which we quantify using established metrics and two new metrics that frame image description as a word recall task. This framing allows us to evaluate system performance on the head of the vocabulary, as well as on the long tail, where system performance degrades. We use these metrics to examine the diversity of the sentences generated by nine state-of-the-art systems on the MS COCO data set. We find that the systems trained with maximum likelihood objectives produce less diverse output than those trained with additional adversarial objectives. However, the adversarially-trained models only produce more types from the head of the vocabulary and not the tail. Besides vocabulary-based methods, we also look at the compositional capacity of the systems, specifically their ability to create compound nouns and prepositional phrases of different lengths. We conclude that there is still much room for improvement, and offer a toolkit to measure progress towards the goal of generating more diverse image descriptions. |
| Tasks | Text Generation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1147/ |
| https://www.aclweb.org/anthology/C18-1147 | |
| PWC | https://paperswithcode.com/paper/measuring-the-diversity-of-automatic-image |
| Repo | https://github.com/evanmiltenburg/MeasureDiversity |
| Framework | none |
Challenges in Finding Metaphorical Connections
| Title | Challenges in Finding Metaphorical Connections |
| Authors | Katy Gero, Lydia Chilton |
| Abstract | Poetry is known for its novel expression using figurative language. We introduce a writing task that contains the essential challenges of generating meaningful figurative language and can be evaluated. We investigate how to find metaphorical connections between abstract themes and concrete domains by asking people to write four-line poems on a given metaphor, such as {}death is a rose{''} or {}anger is wood{''}. We find that only 21{%} of poems successfully make a metaphorical connection. We present five alternate ways people respond to the prompt and release our dataset of 100 categorized poems. We suggest opportunities for computational approaches. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0901/ |
| https://www.aclweb.org/anthology/W18-0901 | |
| PWC | https://paperswithcode.com/paper/challenges-in-finding-metaphorical |
| Repo | https://github.com/kgero/metaphorical-connections |
| Framework | none |
DeepCalib: a deep learning approach for automatic intrinsic calibration of wide field-of-view cameras
| Title | DeepCalib: a deep learning approach for automatic intrinsic calibration of wide field-of-view cameras |
| Authors | Oleksandr Bogdan, Viktor Eckstein, Francois Rameau, Jean-Charles Bazin |
| Abstract | Calibration of wide field-of-view cameras is a fundamental step for numerous visual media production applications, such as 3D reconstruction, image undistortion, augmented reality and camera motion estimation. However, existing calibration methods require multiple images of a calibration pattern (typically a checkerboard), assume the presence of lines, require manual interaction and/or need an image sequence. In contrast, we present a novel fully automatic deep learning-based approach that overcomes all these limitations and works with a single image of general scenes. Our approach builds upon the recent developments in deep Convolutional Neural Networks (CNN): our network automatically estimates the intrinsic parameters of the camera (focal length and distortion parameter) from a single input image. In order to train the CNN, we leverage the great amount of omnidirectional images available on the Internet to automatically generate a large-scale dataset composed of millions of wide field-of-view images with ground truth intrinsic parameters. Experiments successfully demonstrated the quality of our results, both quantitatively and qualitatively. |
| Tasks | 3D Reconstruction, Calibration, Motion Estimation |
| Published | 2018-12-15 |
| URL | https://dl.acm.org/doi/10.1145/3278471.3278479 |
| https://www.researchgate.net/publication/329226174_DeepCalib_a_deep_learning_approach_for_automatic_intrinsic_calibration_of_wide_field-of-view_cameras | |
| PWC | https://paperswithcode.com/paper/deepcalib-a-deep-learning-approach-for |
| Repo | https://github.com/alexvbogdan/DeepCalib |
| Framework | tf |
Pulmonary vessel tree matching for quantifying changes in vascular morphology
| Title | Pulmonary vessel tree matching for quantifying changes in vascular morphology |
| Authors | Zhiwei Zhai, Marius Staring, Hideki Ota, Berend C. Stoel |
| Abstract | Invasive right-sided heart catheterization (RHC) is currently the gold standard for assessing treatment effects in pulmonary vascular diseases, such as chronic thromboembolic pulmonary hypertension (CTEPH). Quantifying morphological changes by matching vascular trees (pre- and post-treatment) may provide a non-invasive alternative for assessing hemodynamic changes. In this work, we propose a method for quantifying morphological changes, consisting of three steps: constructing vascular trees from the detected pulmonary vessels, matching vascular trees with preserving local tree topology, and quantifying local morphological changes based on Poiseuille’s law (changes in radius−4 , △r−4 ). Subsequently, median and interquartile range (IQR) of all local △r−4 were calculated as global measurements for assessing morphological changes. The vascular tree matching method was validated with 10 synthetic trees and the relation between clinical RHC parameters and quantifications of morphological changes was investigated in 14 CTEPH patients, pre- and post-treatment. In the evaluation with synthetic trees, the proposed method achieved an average residual distance of 3.09±1.28 mm, which is a substantial improvement over the coherent point drift method ( 4.32±1.89 mm) and a method with global-local topology preservation ( 3.92±1.59 mm). In the clinical evaluation, the morphological changes (IQR of △r−4 ) was significantly correlated with the changes in RHC examinations, △sPAP ( R=−0.62 , p-value = 0.019) and △mPAP ( R=−0.56 , p-value = 0.038). Quantifying morphological changes may provide a non-invasive assessment of treatment effects in CTEPH patients, consistent with hemodynamic changes from invasive RHC. |
| Tasks | |
| Published | 2018-09-26 |
| URL | https://link.springer.com/chapter/10.1007/978-3-030-00934-2_58 |
| https://link.springer.com/content/pdf/10.1007%2F978-3-030-00934-2_58.pdf | |
| PWC | https://paperswithcode.com/paper/pulmonary-vessel-tree-matching-for |
| Repo | https://github.com/chushan89/pulmonary-vascular-tree-matching |
| Framework | none |
NLATool: an Application for Enhanced Deep Text Understanding
| Title | NLATool: an Application for Enhanced Deep Text Understanding |
| Authors | Markus G{"a}rtner, Sven Mayer, Valentin Schwind, Eric H{"a}mmerle, Emine Turcan, Florin Rheinwald, Gustav Murawski, Lars Lischke, Jonas Kuhn |
| Abstract | Today, we see an ever growing number of tools supporting text annotation. Each of these tools is optimized for specific use-cases such as named entity recognition. However, we see large growing knowledge bases such as Wikipedia or the Google Knowledge Graph. In this paper, we introduce NLATool, a web application developed using a human-centered design process. The application combines supporting text annotation and enriching the text with additional information from a number of sources directly within the application. The tool assists users to efficiently recognize named entities, annotate text, and automatically provide users additional information while solving deep text understanding tasks. |
| Tasks | Coreference Resolution, Entity Linking, Named Entity Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2026/ |
| https://www.aclweb.org/anthology/C18-2026 | |
| PWC | https://paperswithcode.com/paper/nlatool-an-application-for-enhanced-deep-text |
| Repo | https://github.com/interactionlab/NLATool |
| Framework | none |
Multilingual Dependency Parsing for Low-Resource Languages: Case Studies on North Saami and Komi-Zyrian
| Title | Multilingual Dependency Parsing for Low-Resource Languages: Case Studies on North Saami and Komi-Zyrian |
| Authors | KyungTae Lim, Niko Partanen, Thierry Poibeau |
| Abstract | |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Multilingual Word Embeddings, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1352/ |
| https://www.aclweb.org/anthology/L18-1352 | |
| PWC | https://paperswithcode.com/paper/multilingual-dependency-parsing-for-low |
| Repo | https://github.com/jujbob/multilingual-models |
| Framework | none |
Benchmarking of image registration methods for differently stained histological slides
| Title | Benchmarking of image registration methods for differently stained histological slides |
| Authors | Jiří Borovec, Arrate Muñoz-Barrutia, Jan Kybic |
| Abstract | Image registration is a common task for many biomedical analysis applications. The present work focuses on the benchmarking of registration methods on differently stained histological slides. This is a challenging task due to the differences in the appearance model, the repetitive texture of the details and the large image size, between other issues. Our benchmarking data is composed of 616 image pairs at two different scales — average image diagonal 2.4k and 5k pixels. We compare eleven fully automatic registration methods covering the widely used similarity measures. For each method, the best parameter configuration is found and subsequently applied to all the image pairs. The performance of the algorithms is evaluated from several perspectives — the registrations (in)accuracy on manually annotated landmarks, the method robustness and its computation time. |
| Tasks | BIRL, Image Registration, Medical Image Registration |
| Published | 2018-10-11 |
| URL | https://ieeexplore.ieee.org/document/8451040 |
| https://www.researchgate.net/publication/325019076_Benchmarking_of_Image_Registration_Methods_for_Differently_Stained_Histological_Slides | |
| PWC | https://paperswithcode.com/paper/benchmarking-of-image-registration-methods |
| Repo | https://github.com/Borda/BIRL |
| Framework | none |
A UIMA Database Interface for Managing NLP-related Text Annotations
| Title | A UIMA Database Interface for Managing NLP-related Text Annotations |
| Authors | Giuseppe Abrami, Alex Mehler, er |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1212/ |
| https://www.aclweb.org/anthology/L18-1212 | |
| PWC | https://paperswithcode.com/paper/a-uima-database-interface-for-managing-nlp |
| Repo | https://github.com/texttechnologylab/UIMADatabaseInterface |
| Framework | none |
Prompsit’s submission to WMT 2018 Parallel Corpus Filtering shared task
| Title | Prompsit’s submission to WMT 2018 Parallel Corpus Filtering shared task |
| Authors | V{'\i}ctor M. S{'a}nchez-Cartagena, Marta Ba{~n}{'o}n, Sergio Ortiz-Rojas, Gema Ram{'\i}rez |
| Abstract | This paper describes Prompsit Language Engineering{'}s submissions to the WMT 2018 parallel corpus filtering shared task. Our four submissions were based on an automatic classifier for identifying pairs of sentences that are mutual translations. A set of hand-crafted hard rules for discarding sentences with evident flaws were applied before the classifier. We explored different strategies for achieving a training corpus with diverse vocabulary and fluent sentences: language model scoring, an active-learning-inspired data selection algorithm and n-gram saturation. Our submissions were very competitive in comparison with other participants on the 100 million word training corpus. |
| Tasks | Active Learning, Language Modelling, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6488/ |
| https://www.aclweb.org/anthology/W18-6488 | |
| PWC | https://paperswithcode.com/paper/prompsits-submission-to-wmt-2018-parallel |
| Repo | https://github.com/bitextor/bicleaner |
| Framework | none |
